Qwen 3.8 Coding Test: Nearly Matches K3 at Half the Price

bindureddy · x · 2026-08-04

A developer shared preliminary test results for the Qwen 3.8 model. It performs well in agentic coding tasks, being only slightly worse than the K3 model but twice as cheap, making it the top model in its price range. The author suggests switching from K3 to Qwen 3.8 to cut costs.

Related event: Qwen 3.8 Excels in Agentic Coding Tests(2 posts)→

Original post →

More from coding & agent

coding & agent channel →